research

Warn

Audited by Snyk on Jul 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). SKILL.md describes gathering 5–10 “high-quality sources” from external web/public materials and then applying an ingest workflow to those sources, which implies the LLM will read outsider-authored free text from saved sources/YYYY-MM-DD/ content at runtime for wiki updates.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 25, 2026, 08:53 AM
Issues
1
Security Audit — snyk — research